INDEX

Explanations

questions or statements containing uncertainty

oai_token-act-pair · gpt-3.5-turbo

questions or inquiries about past events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 biodiversity

-0.78

hani

-0.68

 sustainability

-0.67

-0.66

 affordability

-0.66

equality

-0.65

 equality

-0.65

pires

-0.64

 increases

-0.63

POSITIVE LOGITS

Was

1.19

Was

1.09

didn

1.07

 hadn

1.06

Did

1.02

 recalled

1.01

 hindsight

1.01

did

1.00

was

0.99

Had

0.99

Activations Density 0.859%

questions or statements containing uncertainty

questions or inquiries about past events

No Comments

No Known Activations